© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 74900
    Prev
    Next
    INDEX
    Explanations

    text after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron spotlights the actual solution sentences (the imperative-style advice or instructional lines) in an answer.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ингреди
    -1.37
     recueil
    -1.24
    与此同时
    -1.22
    ığımız
    -1.17
     hahaha
    -1.17
     Verfasser
    -1.16
     Synag
    -1.15
     Preisen
    -1.14
     Miß
    -1.13
     peuples
    -1.12
    POSITIVE LOGITS
     so
    1.48
     which
    1.45
    ↵
    1.44
    <eos>
    1.35
     you
    1.34
     podrás
    1.20
     see
    1.18
     eſ
    1.18
    ẖ
    1.11
    weihnachts
    1.08
    Activations Density 0.467%

    No Known Activations